© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13406
    Prev
    Next
    INDEX
    Explanations

    plural markers

    np_acts-logits-general · gemini-2.5-flash-lite

    scientific and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ل
    0.58
    il
    0.54
    gm
    0.53
    ar
    0.52
    el
    0.52
    Value
    0.51
    igare
    0.51
    et
    0.50
    ンダント
    0.50
    According
    0.49
    POSITIVE LOGITS
    們
    1.55
    们
    1.46
    들을
    1.38
    们的
    1.35
    ‌های
    1.31
    ים
    1.29
    들의
    1.29
    들과
    1.28
    들에게
    1.27
    들
    1.25
    Activations Density 1.849%

    No Known Activations